ResBuilder: Automated Learning of Depth with Residual Structures
Abstract
In this work, we develop a neural architecture search algorithm, termed Resbuilder, that develops ResNet architectures from scratch that achieve high accuracy at moderate computational cost. It can also be used to modify existing architectures and has the capability to remove and insert ResNet blocks, in this way searching for suitable architectures in the space of ResNet architectures. In our experiments on different image classification datasets, Resbuilder achieves close to state-of-the-art performance while saving computational cost compared to off-the-shelf ResNets. Noteworthy, we once tune the parameters on CIFAR10 which yields a suitable default choice for all other datasets. We demonstrate that this property generalizes even to industrial applications by applying our method with default parameters on a proprietary fraud detection dataset.
Keywords
Cite
@article{arxiv.2308.08504,
title = {ResBuilder: Automated Learning of Depth with Residual Structures},
author = {Julian Burghoff and Matthias Rottmann and Jill von Conta and Sebastian Schoenen and Andreas Witte and Hanno Gottschalk},
journal= {arXiv preprint arXiv:2308.08504},
year = {2023}
}